Definition. Credit-assignment rule [ftip-0054]
Definition. Credit-assignment rule [ftip-0054]
Let \(R\) be a rollout record with \(\tau _{\rm stop}\) actions, and let \(f\) be its feedback event. A credit-assignment rule returns indexed training targets
\[\mathsf {Credit}(R,f)=(c_0,\ldots ,c_{\tau _{\rm stop}-1}).\]Each \(c_t\) is attached to an action or token position declared by the rule. It may be a return, an advantage estimate, a binary label, or a structured target. The rule is distinct from the feedback source that supplied \(f\).